ATBECHDEDKESFRGBGRITLILUNLSEMCPTIESILTLVFIROMKCYALTRBGCZEEHUPLSKBAHRIS..MTNORSMESMMAKHTNMD..........JBDM Ver 2.0.15 (20th of December) - 1620000/03929866EUROPEAN PATENT APPLICATIONA320220608EP21206464.620211104enenen20211008924520210122CN2022060820222320211229202152G06T 5/00 20060101AFI20220503BHEP G06T 11/00 20060101ALI20220503BHEP G06T 7/11 20170101ALI20220503BHEP G06T 5/005 20130101 FI20220120BHEP G06T2207/10024 20130101 LA20220120BHEP G06T2207/20081 20130101 LA20220120BHEP G06T2207/20084 20130101 LA20220120BHEP G06T2207/30196 20130101 LA20220120BHEP deINPAINTING-VERFAHREN UND -VORRICHTUNG FÜR EIN MENSCHLICHES BILD UND ELEKTRONISCHE VORRICHTUNGenINPAINTING METHOD AND APPARATUS FOR HUMAN IMAGE, AND ELECTRONIC DEVICEfrPROCÉDÉ DE RETOUCHE ET APPAREIL POUR IMAGE HUMAINE, ET DISPOSITIF ÉLECTRONIQUE1BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.101848235B17451EP/HLZ2/F Baidu CampusNo. 10 Shangdi 10th Street Haidian District Beijing 100085CNZou, ZhikangBeijing, 100085CNYe, XiaoqingBeijing, 100085CNChen, QuBeijing, 100085CNSun, HaoBeijing, 100085CNMaiwald Patent- und Rechtsanwaltsgesellschaft mbH100061181Elisenhof Elisenstraße 380335 MünchenDEALATBEBGCHCYCZDEDKEEESFIFRGBGRHRHUIEISITLILTLULVMCMKMTNLNOPLPTRORSSESISKSMTRBAMEKHMAMDTN20220608202223

The disclosure provides an inpainting method for a human image, an inpainting apparatus for a human image and an electronic device. An image to be processed is received (S101). The image to be processed contains a human image to be processed. A three-dimensional human body model corresponding to the human image to be processed, camera parameters, and human body posture information are generated (S102) based on the image to be processed. A segmentation image corresponding to the human image to be processed is generated (S103) based on the image to be processed. A processed human image corresponding to the human image to be processed is generated (S104) based on the three-dimensional human body model, the camera parameters, the human body posture information, and the segmentation image.

B17451EP/HLZEP21206464.6BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.1MN20220510G06T
ZHANG TIANSHU ET ALObject-Occluded Human Shape and Pose Estimation From a Single Color Image2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), IEEE2020061310.1109/CVPR42600.2020.0074073747383XP033803394
X1-4,10-15* abstract; figures 1, 3, 5 ** page 7377, paragraph 2 ** page 7378, paragraph 1 ** "3. Method";page 7376 - page 7378 *
PAVLAKOS GEORGIOS ET ALExpressive Body Capture: 3D Hands, Face, and Body From a Single Image2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), IEEE2019061510.1109/CVPR.2019.011231096710977XP033686409
X1-4,10-15* abstract; figures 1, 2 ** "3. Technical approach";page 10970 - page 10972 ** "Conclusion";page 10974 *MEHRA SETIKA ET ALFrom Textural Inpainting to Deep Generative Models: An Extensive Survey of Image Inpainting TechniquesJOURNAL OF COMPUTER SCIENCEUnited States202001011613549https://thescipub.com/pdf/jcssp.2020.35.49.pdf1549-3636XP055916115A1-15* the whole document *Rodes Arnau, IsabelMunich20220429